Fully convolutional network for simultaneous Age/Gender recognition. The network is able to recognize age of people in [18, 75] years old range, it is not applicable for children since their faces were not in the training set.
~20,000 unique subjects representing diverse ages, genders, and ethnicities.
| Input Image | Result |
|---|---|
 |
Female, 18.97 |
 |
Male, 26.52 |
 |
Male, 33.41 |
| Metric | Value |
|---|---|
| Rotation in-plane | ±45˚ |
| Rotation out-of-plane | Yaw: ±45˚ / Pitch: ±45˚ |
| Min object width | 62 pixels |
| GFlops | 0.094 |
| MParams | 2.138 |
| Source framework | Caffe* |
| Metric | Value |
|---|---|
| Avg. age error | 6.99 years |
| Gender accuracy | 95.80% |
Name: input, shape: [1x3x62x62] - An input image in [1xCxHxW] format. Expected color order is BGR.
- Name:
age_conv3, shape: [1, 1, 1, 1] - Estimated age divided by 100. - Name:
prob, shape: [1, 2, 1, 1] - Softmax output across 2 type classes [female, male].
[*] Other names and brands may be claimed as the property of others.